当前位置: X-MOL 学术Geoderma › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Characterizing plant root parameters with deep learning-based heat pulse method
Geoderma ( IF 5.6 ) Pub Date : 2021-10-06 , DOI: 10.1016/j.geoderma.2021.115507
Xiaoting Xie 1 , Hengnian Yan 1 , Lingzao Zeng 1, 2
Affiliation  

Accurate quantification of root structure is essential for understanding plant ecological system. Nevertheless, the lack of in-situ root characterization methods has limited further research of the relevant field. Heat pulse (HP) technique has emerged as a promising, cost-effective in situ monitoring approach. The existing HP technique relies on the analytical solution of heat transfer model with the assumption that the medium under test is homogeneous. Thus, its performance is compromised in dealing with heterogeneous formations. The objective of this study is to establish a novel in-situ HP method to characterize root parameters based on a deep learning technique. With the fully connected neural networks (FCNN), the number of root fragments was firstly estimated by solving a classification problem, and then the size and location of each fragment were estimated by solving regression problems. All FCNNs were firstly pre-trained using synthetic dataset generated by the numerical heat transfer model. Although FCNNs showed promising accuracy on the synthetic testing dataset, they failed to provide satisfactory results on real-world experimental data due to the model error and observation noise, i.e., the deviations between the numerical model and actual situation. To this end, FCNNs were fine-tuned with some experimental data through transfer learning for performance improvement. Under controlled indoor experiment in a sandy soil, the proposed method provided satisfactory results for the estimation of root fragment number and diameters with 83.3% accuracy and RMSE of 1.87 × 10−4 m, respectively. The position estimation had relatively larger error, i.e., RMSE 2.41 × 10−3 m. This study is the first step in translating heat pulse signals to root parameters, which indicates the potential of combining HP technique and deep learning in studying root system.



中文翻译:

用基于深度学习的热脉冲方法表征植物根参数

根结构的准确量化对于理解植物生态系统至关重要。然而,原位根表征方法的缺乏限制了相关领域的进一步研究。热脉冲 (HP) 技术已成为一种有前途、具有成本效益的原位监测方法。现有的 HP 技术依赖于传热模型的解析解,并假设被测介质是均质的。因此,它的性能在处理异质地层时受到影响。本研究的目的是建立一种新的原位 HP 方法来表征基于深度学习技术的根参数。使用全连接神经网络(FCNN),首先通过解决分类问题来估计根片段的数量,然后通过求解回归问题估计每个片段的大小和位置。所有 FCNN 首先使用由数值传热模型生成的合成数据集进行预训练。尽管 FCNN 在合成测试数据集上表现出良好的准确性,但由于模型误差和观察噪声,即数值模型与实际情况之间的偏差,它们未能在真实世界的实验数据上提供令人满意的结果。为此,通过迁移学习对 FCNN 进行了一些实验数据的微调,以提高性能。在沙质土壤的室内受控实验下,该方法为估计根碎片数和直径提供了令人满意的结果,准确度为 83.3%,RMSE 为 1.87 × 10 所有 FCNN 首先使用由数值传热模型生成的合成数据集进行预训练。尽管 FCNN 在合成测试数据集上表现出良好的准确性,但由于模型误差和观察噪声,即数值模型与实际情况之间的偏差,它们未能在真实世界的实验数据上提供令人满意的结果。为此,通过迁移学习对 FCNN 进行了一些实验数据的微调,以提高性能。在沙质土壤的室内受控实验下,该方法为估计根碎片数和直径提供了令人满意的结果,准确度为 83.3%,RMSE 为 1.87 × 10 所有 FCNN 首先使用由数值传热模型生成的合成数据集进行预训练。尽管 FCNN 在合成测试数据集上表现出良好的准确性,但由于模型误差和观察噪声,即数值模型与实际情况之间的偏差,它们未能在真实世界的实验数据上提供令人满意的结果。为此,通过迁移学习对 FCNN 进行了一些实验数据的微调,以提高性能。在沙质土壤的室内受控实验下,该方法为估计根碎片数和直径提供了令人满意的结果,准确度为 83.3%,RMSE 为 1.87 × 10 由于模型误差和观测噪声,即数值模型与实际情况之间的偏差,他们未能在现实世界的实验数据上提供令人满意的结果。为此,通过迁移学习对 FCNN 进行了一些实验数据的微调,以提高性能。在沙质土壤的室内受控实验下,该方法为估计根碎片数和直径提供了令人满意的结果,准确度为 83.3%,RMSE 为 1.87 × 10 由于模型误差和观测噪声,即数值模型与实际情况之间的偏差,他们未能在现实世界的实验数据上提供令人满意的结果。为此,通过迁移学习对 FCNN 进行了一些实验数据的微调,以提高性能。在沙质土壤的室内受控实验下,该方法为估计根碎片数和直径提供了令人满意的结果,准确度为 83.3%,RMSE 为 1.87 × 10-4 m,分别。位置估计具有相对较大的误差,即RMSE 2.41 × 10 -3 m。这项研究是将热脉冲信号转换为根参数的第一步,这表明结合 HP 技术和深度学习在研究根系方面具有潜力。

更新日期:2021-10-06
down
wechat
bug